Unsupervised Learning of Overlapping Image Components Using Divisive Input Modulation
Performance of each algorithm when trained on
the overlapping squares task with (a) , (b) , and (c) . Results are shown for three different versions of
each task; foreground bars show results when equals the
number of image components, , and ; middle bars show results for , , and ; background bars show results for , , and . Results are averaged over 10 trials for each
condition. Plots in the left-hand column show the mean number of errors
generated in the response of each network to 1000 test images. Each bar is
subdivided into the proportion of false negatives (lighter, lower, section) and
the proportion of false positives (darker, upper, section). Plots in the
right-hand column show the mean number of components correctly represented by
the synaptic weights learnt by each algorithm. Error bars show best and worst
performance, across the 10 trials.
Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.